All Projects → Dojocat-GO → Tencent2017_Final_Rank28_code

Dojocat-GO / Tencent2017_Final_Rank28_code

Licence: other
2017第一届腾讯社交广告高校算法大赛Rank28_code

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Tencent2017 Final Rank28 code

Dc Hi guides
[Data Castle 算法竞赛] 精品旅行服务成单预测 final rank 11
Stars: ✭ 83 (-2.35%)
Mutual labels:  data-mining, xgboost, lightgbm
JLBoost.jl
A 100%-Julia implementation of Gradient-Boosting Regression Tree algorithms
Stars: ✭ 65 (-23.53%)
Mutual labels:  xgboost, lightgbm
fast retraining
Show how to perform fast retraining with LightGBM in different business cases
Stars: ✭ 56 (-34.12%)
Mutual labels:  xgboost, lightgbm
Kaggle-Competition-Sberbank
Top 1% rankings (22/3270) code sharing for Kaggle competition Sberbank Russian Housing Market: https://www.kaggle.com/c/sberbank-russian-housing-market
Stars: ✭ 31 (-63.53%)
Mutual labels:  xgboost, lightgbm
Lightgbm
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Stars: ✭ 13,293 (+15538.82%)
Mutual labels:  data-mining, lightgbm
docker-kaggle-ko
머신러닝/딥러닝(PyTorch, TensorFlow) 전용 도커입니다. 한글 폰트, 한글 자연어처리 패키지(konlpy), 형태소 분석기, Timezone 등의 설정 등을 추가 하였습니다.
Stars: ✭ 46 (-45.88%)
Mutual labels:  xgboost, lightgbm
neptune-client
📒 Experiment tracking tool and model registry
Stars: ✭ 348 (+309.41%)
Mutual labels:  xgboost, lightgbm
Mli Resources
H2O.ai Machine Learning Interpretability Resources
Stars: ✭ 428 (+403.53%)
Mutual labels:  data-mining, xgboost
Kaggle
Kaggle Kernels (Python, R, Jupyter Notebooks)
Stars: ✭ 26 (-69.41%)
Mutual labels:  xgboost, lightgbm
AutoTabular
Automatic machine learning for tabular data. ⚡🔥⚡
Stars: ✭ 51 (-40%)
Mutual labels:  xgboost, lightgbm
mlforecast
Scalable machine 🤖 learning for time series forecasting.
Stars: ✭ 96 (+12.94%)
Mutual labels:  xgboost, lightgbm
recsys2019
The complete code and notebooks used for the ACM Recommender Systems Challenge 2019
Stars: ✭ 26 (-69.41%)
Mutual labels:  xgboost, lightgbm
Apartment-Interest-Prediction
Predict people interest in renting specific NYC apartments. The challenge combines structured data, geolocalization, time data, free text and images.
Stars: ✭ 17 (-80%)
Mutual labels:  xgboost, lightgbm
decision-trees-for-ml
Building Decision Trees From Scratch In Python
Stars: ✭ 61 (-28.24%)
Mutual labels:  xgboost, lightgbm
Rong360
用户贷款风险预测
Stars: ✭ 489 (+475.29%)
Mutual labels:  data-mining, xgboost
stackgbm
🌳 Stacked Gradient Boosting Machines
Stars: ✭ 24 (-71.76%)
Mutual labels:  xgboost, lightgbm
diabetes use case
Sample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/
Stars: ✭ 22 (-74.12%)
Mutual labels:  data-mining, xgboost
Alink
Alink is the Machine Learning algorithm platform based on Flink, developed by the PAI team of Alibaba computing platform.
Stars: ✭ 2,936 (+3354.12%)
Mutual labels:  data-mining, xgboost
MSDS696-Masters-Final-Project
Earthquake Prediction Challenge with LightGBM and XGBoost
Stars: ✭ 58 (-31.76%)
Mutual labels:  xgboost, lightgbm
datascienv
datascienv is package that helps you to setup your environment in single line of code with all dependency and it is also include pyforest that provide single line of import all required ml libraries
Stars: ✭ 53 (-37.65%)
Mutual labels:  xgboost, lightgbm

Tencent2017_Final_Rank28_code

2017第一届腾讯社交广告高校算法大赛Rank28_code 赛题详情:http://algo.tpai.qq.com/home/information/index.html

题目描述

计算广告是互联网最重要的商业模式之一,广告投放效果通常通过曝光、点击和转化各环节来衡量,大多数广告系统受广告效果数据回流的限制只能通过曝光或点击作为投放效果的衡量标准开展优化。腾讯社交广告(http://ads.tencent.com) 发挥特有的用户识别和转化跟踪数据能力,帮助广告主跟踪广告投放后的转化效果,基于广告转化数据训练转化率预估模型(pCVR,Predicted Conversion Rate),在广告排序中引入pCVR因子优化广告投放效果,提升ROI。

本题目以移动App广告为研究对象,预测App广告点击后被激活的概率:pCVR=P(conversion=1 | Ad,User,Context),即给定广告、用户和上下文情况下广告被点击后发生激活的概率。

代码描述

按照代码标号顺序逐个生成特征csv文件,代码内有相应特征说明。生成特征之后运行lgb和xgb文件模型代码分别得到2个模型的预测结果。

##代码运行之前下载决赛数据集(http://spabigdata-1253211098.cosgz.myqcloud.com/final.zip),解压至Tencent文件夹下。

最终提交特征由基础特征,交叉特征,统计特征,转化率特征和trick特征组成,共计100维左右,建议运行在32G内存以上机器。

模型方面用到xgboost,lightgbm,第一次参赛,经验不足,决赛前期因线上线下得分不一致,花费太多时间在数据集构建上,导致没有充分的时间筛选特征,
没有stacking融合,模型参数也没有调到最优,遗憾未能进入前二十。

最终提交结果得分:0.101972,由xgb,lgb预测结果平均得到。
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].